Comparison of radiomics approaches to predict resistance to 1st line chemotherapy in liver metastatic colorectal cancer.

Colorectal cancer (CRC) has the second-highest tumor incidence and is a leading cause of death by cancer. Nearly 20% of patients with CRC will have metastases (mts) at the time of diagnosis, and more than 50% of patients with CRC develop metastases during their disease. Unfortunately, only 45% of patients after a chemotherapy will respond to treatment. The aim of this study is to develop and validate a machine learning algorithm to predict response of individual liver mts, using CT scans. Understanding which mts will respond or not will help clinicians in providing a more efficient per-lesion treatment based on patient specific response and not only following a standard treatment. A group of 92 patients was enrolled from two Italian institutions. CT scans were collected, and the portal venous phase was manually segmented by an expert radiologist. Then, 75 radiomics features were extracted both from 7x7 ROIs that moved across the image and from the whole 3D mts. Feature selection was performed using a genetic algorithm. Results are presented as a comparison of the two different approaches of features extraction and different classification algorithms. Accuracy (ACC), sensitivity (SE), specificity (SP), negative and positive predictive values (NPV and PPV) were evaluated for all lesions (per-lesion analysis) and patients (per-patient analysis) in the construction and validation sets. Best results were obtained in the per-lesion analysis from the 3D approach using a Support Vector Machine as classifier. We reached on the training set an ACC of 81%, while on test set, we obtained SE of 76%, SP of 67%, PPV of 69% and NPV of 75%. On the validation set a SE of 61%, SP of 60%, PPV of 57% and NPV of 64% were reached. The promising results obtained in the validation dataset should be extended to a larger cohort of patient to further validate our method.Clinical Relevance- to develop a radiomics signatures predicting single liver mts response to therapy. A personalized mts approach is important to avoid unnecessary toxicity offering more suitable treatments and a better quality of life to oncological patients.

Deep learning model for automatic prostate segmentation on bicentric T2w images with and without endorectal coil.

Automatic segmentation of the prostate on Magnetic Resonance Imaging (MRI) is one of the topics on which research has focused in recent years as it is a fundamental first step in the building process of a Computer aided diagnosis (CAD) system for cancer detection. Unfortunately, MRI acquired in different centers with different scanners leads to images with different characteristics. In this work, we propose an automatic algorithm for prostate segmentation, based on a U-Net applying transfer learning method in a bi-center setting. First, T2w images with and without endorectal coil from 80 patients acquired at Center A were used as training set and internal validation set. Then, T2w images without endorectal coil from 20 patients acquired at Center B were used as external validation. The reference standard for this study was manual segmentation of the prostate gland performed by an expert operator. The results showed a Dice similarity coefficient >85% in both internal and external validation datasets.Clinical Relevance- This segmentation algorithm could be integrated into a CAD system to optimize computational effort in prostate cancer detection.

Virtual biopsy in prostate cancer: can machine learning distinguish low and high aggressive tumors on MRI?

In the last decades, MRI was proven a useful tool for the diagnosis and characterization of Prostate Cancer (PCa). In the literature, many studies focused on characterizing PCa aggressiveness, but a few have distinguished between low-aggressive (Gleason Grade Group (GG) <=2) and high-aggressive (GG>=3) PCas based on biparametric MRI (bpMRI). In this study, 108 PCas were collected from two different centers and were divided into training, testing, and validation set. From Apparent Diffusion Coefficient (ADC) map and T2-Weighted Image (T2WI), we extracted texture features, both 3D and 2D, and we implemented three different methods of Feature Selection (FS): Minimum Redundance Maximum Relevance (MRMR), Affinity Propagation (AP), and Genetic Algorithm (GA). From the resulting subsets of predictors, we trained Support Vector Machine (SVM), Decision Tree, and Ensemble Learning classifiers on the training set, and we evaluated their prediction ability on the testing set. Then, for each FS method, we chose the best classifier, based on both training and testing performances, and we further assessed their generalization capability on the validation set. Between the three best models, a Decision Tree was trained using only two features extracted from the ADC map and selected by MRMR, achieving, on the validation set, an Area Under the ROC (AUC) equal to 81%, with sensitivity and specificity of 77% and 93%, respectively.Clinical Relevance- Our best model demonstrated to be able to distinguish low-aggressive from high-aggressive PCas with high accuracy. Potentially, this approach could help clinician to noninvasively distinguish between PCas that might need active treatment and those that could potentially benefit from active surveillance, avoiding biopsy-related complications.